Advertisement

Evolutionary Intelligence

, Volume 12, Issue 4, pp 593–608 | Cite as

A new genetically optimized tensor product functional link neural network: an application to the daily exchange rate forecasting

  • Waddah Waheeb
  • Rozaida GhazaliEmail author
Research Paper

Abstract

The training speed for multilayer neural networks is slow due to the multilayering. Therefore, removing the hidden layers, provided that the input layer is endowed with additional higher order units is suggested to avoid such problem. Tensor product functional link neural network (TPFLNN) is a single layer with higher order terms that extend the network’s structure by introducing supplementary inputs to the network (i.e., joint activations). Although the structure of the TPFLNN is simple, it suffers from weight combinatorial explosion problem when its order becomes excessively high. Furthermore, similarly to many neural network methods, selection of proper weights is one of the most challenging issues in the TPFLNN. Finding suitable weights could help to reduce the number of needed weights. Therefore, in this study, the genetic algorithm (GA) was used to find near-optimum weights for the TPFLNN. The proposed method is abbreviated as GA–TPFLNN. The GA–TPFLNN was used to forecast the daily exchange rate for the Euro/US Dollar, and Japanese Yen/US Dollar. Simulation results showed that the GA–TPFLNN produced more accurate forecasts as compared to the standard TPFLNN, GA, GA–TPFLNN with backpropagation, GA-functional expansion FLNN, multilayer perceptron, support vector regression, random forests for regression, and naive methods. The GA helps the TPFLNN to find low complexity network structure and/or near-optimum parameters which leads to this better result.

Keywords

Functional link neural network Genetic algorithm Exchange rate Time series Forecasting 

Notes

Acknowledgements

The authors would like to thank Universiti Tun Hussein Onn Malaysia and the Office for Research, Innovation, Commercialization and Consultancy Management (ORICC) for funding this research under the Postgraduate Research Grant (GPPS), VOT # U612.

References

  1. 1.
    Rout AK, Dash P, Dash R, Bisoi R (2017) Forecasting financial time series using a low complexity recurrent neural network and evolutionary learning approach. J King Saud Univ Comput Inf Sci 29(4):536–552.  https://doi.org/10.1016/j.jksuci.2015.06.002 CrossRefGoogle Scholar
  2. 2.
    Zhang G, Patuwo BE, Hu MY (1998) Forecasting with artificial neural networks: the state of the art. Int J Forecast 14(1):35–62.  https://doi.org/10.1016/S0169-2070(97)00044-7 CrossRefGoogle Scholar
  3. 3.
    Dehuri S, Cho SB (2010) Evolutionarily optimized features in functional link neural network for classification. Expert Syst Appl 37(6):4379–4391.  https://doi.org/10.1016/j.eswa.2009.11.090 CrossRefGoogle Scholar
  4. 4.
    Waheeb W, Ghazali R (2016) Chaotic time series forecasting using higher order neural networks. Int J Adv Sci Eng Inf Technol.  https://doi.org/10.18517/ijaseit.6.5.958 CrossRefGoogle Scholar
  5. 5.
    Pao Y (1989) Adaptive pattern recognition and neural networks. Addison-Wesley, ReadingzbMATHGoogle Scholar
  6. 6.
    Ghazali R (2007) Higher order neural networks for financial time series prediction. PhD thesis, Liverpool John Moores UniversityGoogle Scholar
  7. 7.
    Giles CL, Maxwell T (1987) Learning, invariance, and generalization in high-order neural networks. Appl Opt 26(23):4972–4978.  https://doi.org/10.1364/AO.26.004972 CrossRefGoogle Scholar
  8. 8.
    Dehuri S, Cho SB (2010) A comprehensive survey on functional link neural networks and an adaptive PSO–BP learning for CFLNN. Neural Comput Appl 19(2):187–205.  https://doi.org/10.1007/s00521-009-0288-5 CrossRefGoogle Scholar
  9. 9.
    Pao YH, Beer RD (1988) The functional link net: a unifying network architecture incorporating higher order effects. Neural Netw 1:40.  https://doi.org/10.1016/0893-6080(88)90082-2 (iNNS 1st annual meeting)CrossRefGoogle Scholar
  10. 10.
    Patra JC, van den Bos A (2000) Modeling of an intelligent pressure sensor using functional link artificial neural networks. ISA Trans 39(1):15–27.  https://doi.org/10.1016/S0019-0578(99)00035-X CrossRefGoogle Scholar
  11. 11.
    Haykin S (1999) Neural networks, vol 2. Prentice Hall, New YorkzbMATHGoogle Scholar
  12. 12.
    Kumar DMV, Srivastava SC (1999) Power system state forecasting using artificial neural networks. Electric Mach Power Syst 27(6):653–664.  https://doi.org/10.1080/073135699269091 CrossRefGoogle Scholar
  13. 13.
    Bt Abu Bakar SZ, Bt Ghazali R, Bin Ismail LH (2014) Implementation of modified cuckoo search algorithm on functional link neural network for temperature and relative humidity prediction. Springer, Singapore, pp 151–158Google Scholar
  14. 14.
    Mohmad-Hassim YM, Ghazali R (2013) An improved functional link neural network learning using artificial bee colony optimisation for time series prediction. Int J Bus Intell Data Min 13(8(4)):307–318CrossRefGoogle Scholar
  15. 15.
    Loia V, Parente D, Pedrycz W, Tomasiello S (2018) A granular functional network with delay: some dynamical properties and application to the sign prediction in social networks. Neurocomputing 321:61–71.  https://doi.org/10.1016/j.neucom.2018.08.047 CrossRefGoogle Scholar
  16. 16.
    Castillo E (1998) Functional networks. Neural Process Lett 7(3):151–159.  https://doi.org/10.1023/A:1009656525752 MathSciNetCrossRefGoogle Scholar
  17. 17.
    Holland J (1975) Adaptation in natural and artificial systems. University of Michigan PressGoogle Scholar
  18. 18.
    Goldberg DE (1989) Genetic algorithms in search, optimization and machine learning. Addison-Wesley, BostonzbMATHGoogle Scholar
  19. 19.
    Sierra A, Macias JA, Corbacho F (2001) Evolution of functional link networks. IEEE Trans Evol Comput 5(1):54–65.  https://doi.org/10.1109/4235.910465 CrossRefGoogle Scholar
  20. 20.
    Chen CLP, Bhumireddy C, Darvemula PK (2004) Camera motion classification using a genetic functional-link neural network. In: 2004 IEEE/RSJ international conference on intelligent robots and systems (IROS) (IEEE Cat. No. 04CH37566), vol 3, pp 2343–2348.  https://doi.org/10.1109/IROS.2004.1389759
  21. 21.
    Mili F, Hamdi M (2013) A comparative study of expansion functions for evolutionary hybrid functional link artificial neural networks for data mining and classification. In: 2013 International conference on computer applications technology (ICCAT), pp 1–8.  https://doi.org/10.1109/ICCAT.2013.6521977
  22. 22.
    Benala TR, Dehuri S, Satapathy SC, Madhurakshara S (2012) Genetic algorithm for optimizing functional link artificial neural network based software cost estimation. In: Proceedings of the international conference on information systems design and intelligent applications 2012 (India 2012). Springer, Berlin, pp 75–82Google Scholar
  23. 23.
    Nayak SC, Misra BB, Behera HS (2012) Index prediction with neuro-genetic hybrid network: a comparative analysis of performance. In: 2012 International conference on computing, communication and applications, pp 1–6.  https://doi.org/10.1109/ICCCA.2012.6179215
  24. 24.
    Nguyen T, Tran N, Nguyen BM, Nguyen G (2018) A resource usage prediction system using functional-link and genetic algorithm neural network for multivariate cloud metrics. In: 2018 IEEE 11th conference on service-oriented computing and applications (SOCA), pp 49–56.  https://doi.org/10.1109/SOCA.2018.00014
  25. 25.
    Huang SC, Chuang PJ, Wu CF, Lai HJ (2010) Chaos-based support vector regressions for exchange rate forecasting. Expert Syst Appl 37(12):8590–8598.  https://doi.org/10.1016/j.eswa.2010.06.001 CrossRefGoogle Scholar
  26. 26.
    Hyndman RJ, Athanasopoulos G (2016) Forecasting: principles and practice. OTexts, New YorkGoogle Scholar
  27. 27.
    Waheeb W, Ghazali R, Herawan T (2016) Ridge polynomial neural network with error feedback for time series forecasting. PLoS ONE 11(12):1–34.  https://doi.org/10.1371/journal.pone.0167248 CrossRefGoogle Scholar
  28. 28.
    Waheeb W, Ghazali R, Hussain AJ (2018) Dynamic ridge polynomial neural network with Lyapunov function for time series forecasting. Appl Intell 48(7):1721–1738.  https://doi.org/10.1007/s10489-017-1036-7 CrossRefGoogle Scholar
  29. 29.
    R Core Team (2018) R: a language and environment for statistical computing. R Foundation for Statistical Computing, Vienna. https://www.R-project.org
  30. 30.
    Ripley B, Venables W (2011) nnet: Feed-forward neural networks and multinomial log-linear models. R package version 7(5)Google Scholar
  31. 31.
    Karatzoglou A, Smola A, Hornik K, Zeileis A (2004) kernlab—an S4 package for kernel methods in R. J Stat Softw 11(9):1–20CrossRefGoogle Scholar
  32. 32.
    Liaw A, Wiener M (2002) Classification and regression by randomForest. R News 2(3):18–22Google Scholar
  33. 33.
    MathWorks I (2019) Global optimization toolbox user’s guide. https://www.mathworks.com/help/pdf_doc/gads/gads_tb.pdf

Copyright information

© Springer-Verlag GmbH Germany, part of Springer Nature 2019

Authors and Affiliations

  1. 1.Faculty of Computer Science and Information TechnologyUniversiti Tun Hussein Onn MalaysiaBatu PahatMalaysia
  2. 2.Computer Science DepartmentHodeidah UniversityHodeidahYemen

Personalised recommendations